Edge computing has recently emerged as a promising paradigm to support mobile access in Internet of Things (IoT) multinetworks, where heterogeneous wireless communication solutions coexist. Meanwhile, software-defined networking (SDN) presents a potential infrastructure to monitor and manage mobile edge computing. However, resilient access in the integrated IoT-Edge-SDN environment is a key challenge. In this article, we present location-aware spatio-temporal solution (LASTS) as an edge computing-empowered software-defined system to scalably control mobile IoT access and detect sequential anomaly. LASTS utilizes a Personal access point protocol to enable switching between multiple networks. In addition, it supports efficient control and transfer of the mobile device’s spatio-temporal context. This context information plays an important role in a deep learning model employed for sequential anomaly detection in the LASTS system. Realistic testbed experiments confirm that LASTS can successfully achieve scalable access control and sequential anomaly detection in mobile IoT.

In indoor fire rescue, swift and precise fire source localization and fire severity assessment are pivotal for firefighting strategic planning and casualty evacuation. However, existing solutions primarily focus on detecting fire presence, which do not offer insights into fire's localization and severity. In this paper, we propose UltraFlame, an accurate, user-friendly, and timely system for pinpointing fire sources and assessing fire severity based on acoustic sensing, which bridges significant gaps in fire safety and response. UltraFlame consists of a collocated commodity speaker and microphone pair, sensing fire by emitting inaudible sound waves. We conduct an in-depth investigation of sound propagation impacted by fire combustion, providing physically interpretable data for deep learning framework and enabling fire source localization even without any sound reflection by fire. We dedicatedly establish a correlation between fire severity and sound propagation delays, which serves as an effective indicator for estimating the heated region. Finally, an appropriate deep learning framework is employed to effectively extract temporal and spatial features from channel measurement. Extensive experiments demonstrate that 94% of the localization results have an error of less than 0.8m. Additionally, UltraFlame achieves an accuracy of 96.9% in fire severity assessment across diverse setups, providing real-time and reliable monitoring.

Controller area network (CAN) protocol is an efficient standard enabling communication among electronic control units (ECUs). However, the CAN bus is vulnerable to malicious attacks because of a lack of defense features. In this article, a novel vehicle intrusion detection system (IDS) is developed. The challenge is that existing techniques of IDSs rarely consider attacks with small-batch, which are characterized by their small attack scale and concealed attack patterns, posing a significant threat to driving safety. To solve this problem, we developed an algorithm model that merges multidimensional long short-term memory (MD-LSTM) and self-attention mechanism (SAM), shortly named MULSAM. The MULSAM model was compared with other baseline models, including stacked long short-term memory (LSTM), MD-LSTM, etc. Experiments show that our approach has the best-detection accuracy (98.98%) and training stability. Further, to speed up the inference of MULSAM on edge, the hardware accelerator is implemented on FPGA devices using technologies, such as parallelization, modular, pipeline, and fixed-point quantization. Experiments show that our FPGA-based acceleration scheme has a better-energy efficiency than the CPU platform. Even with a certain degree of quantification, the acceleration model for MULSAM still displays a high-detection accuracy of 98.81% and a low latency of 1.88 ms.

The precise classification of human activities through sensor data collection and analysis addresses the broad demands in healthcare, security surveillance, and smart home applications amidst the rapid development of IoT technology. However, achieving high efficiency and accuracy remains a significant challenge for HAR algorithms. This paper proposes a HAR algorithm based on Transformer and Random Forest (Transformer-RF). The algorithm extracts and integrates multimodal features in the time domain, frequency domain, and statistical metrics, constructing one-dimensional and two-dimensional feature sets through feature transformation. The Transformer component, leveraging self-attention mechanisms, captures long-range dependencies and extracts global contextual information. Concurrently, the Random Forest component randomly selects features and samples, enhancing model diversity and improving complex human activity recognization capabilities. Experimental results demonstrate that compared with state-of-the-art algorithms, the Transformer-RF model achieves superior performance on both one-dimensional and two-dimensional feature sets, with an accuracy of up to 94.17%. The primary contribution of this paper lies in the introduction of an innovative Transformer-RF human activity recognization method, which not only ensures high accuracy but also exhibits excellent generalization capability and practical application potential. This study provides new insights and technical solutions for the field of human activity recognization, offering significant theoretical and practical value.

Human Activity Recognition has been extensively applied to fulfill tasks such as fall detection, human-computer interaction, virtual reality, etc. Existing radio frequency-based HAR methods, although overcoming limitations of wearable-, visual-, and acoustic-based sensing technology, still suffer from high costs and low efficiency, which limits their pervasive use. In this paper, we propose LoDiHAR, a low-cost, distributed HAR system leveraging Radio Frequency Identification technology. LoDiHAR employs low-cost and fully programmable commercial wireless components, providing full access to the PHY samples of the backscattered signals, in which signal phases can be extracted to infer different activities. Different from COTS RFID systems that adopt a polling interrogation scheme, LoDiHAR supports a distributed sensing scheme, which profiles human activities more efficiently. LoDiHAR addresses a series of technical challenges such as accurate phase extraction from backscattered signals, asynchronous distributed RF data fusion and insufficient training data. A Conditional Generative Adversarial Network framework combined with a Transformer model is designed for accurate time-series activity classification. LoDiHAR demonstrates pro-ficiency in recognizing eight types of human activities across diverse environments, achieving an accuracy of up to 94.9% while only costing 10% of the mainstream COTS RFID systems.

Quantized neural networks (QNNs) have become a standard operation for efficiently deploying deep learning models on hardware platforms in real application scenarios. An empirical study on German traffic sign recognition benchmark (GTSRB) dataset shows that under the three white-box adversarial attacks of fast gradient sign method, random + fast gradient sign method and basic iterative method, the accuracy of the full quantization model was only 55%, much lower than that of the full precision model (73%). This indicates the adversarial robustness of the full quantization model is much worse than that of the full precision model. To improve the adversarial robustness of the full quantization model, we have designed an adversarial attack defense platform based on field-programmable gate array (FPGA) to jointly optimize the efficiency and robustness of QNNs. Various hardware-friendly techniques such as adversarial training and feature squeezing were studied and transferred to the FPGA platform based on the designed accelerator of QNN. Experiments on the GTSRB dataset show that the adversarial training embedded on FPGA can increase the model's average accuracy by 2.5% on clean data, 15% under white-box attacks, and 4% under black-box attacks, respectively, demonstrating our methodology can improve the robustness of the full quantization model under different adversarial attacks.

NFC tag authentication is crucial for preventing tag misuse. Existing NFC fingerprinting methods use physical-layer signals, which incorporate tag hardware imperfections, for authentication purposes. However, these methods suffer from limitations such as low scalability for a large number of tags or incompatibility with various NFC protocols, hindering practical application. To address these issues, we propose a new NFC fingerprinting scheme called NFChain$^+$. Instead of sticking to the NFC resonant frequency, NFChain$^+$excavates the tag hardware uniqueness from the protocol-agnostic tag response signal using an agile and compatible frequency band of NFC to extract the tag fingerprint from a chain of tag responses over multiple frequencies. This significantly improves fingerprint scalability. However, extracting the desired fingerprint presents two challenges: fingerprint inconsistency under different configurations, and fingerprint variations due to the signal noise in generic readers. To overcome these challenges, we design an effective signal elimination method to remove the effect of device configurations and employ contrastive learning to reduce fingerprint variations for accurate tag authentication. We further cultivate a data augmentation strategy to save the cost of manually collecting fingerprint measurements for training the authentication model. Extensive experiments show that we can achieve as low as 3.4% FRR and 4.1% FAR for over 600 NFC tags.

IEEE INFOCOM 2023 - IEEE Conference on Computer Communications, New York City, NY, USA, 17-20 May 2023

As a promising way, controlling smart devices through gestures offers the benefits of non-contact interaction, efficiency and convenience. Previous researches on acoustic-based gesture recognition have mostly focused on near-field gestures within 1 meter and for a single user only. However, such a nearfield sensing scheme is inadequate to meet the growing demands for multi-person human-computer interaction in far-field spaces. In this paper, we present a novel acoustic-based room-scale gesture recognition system that is capable of recognizing gestures simultaneously performed by multi-user. Our approach achieves far-field sensing by examining the relationship between acoustic signal frame length and sensing range, and overcoming a series of practical challenges incurred by far-field sensing. To simultaneously detect and distinguish gestures of multiple persons, we divide the sensing area into multiple beamforming sub-scanning areas and apply binary search to detect multiple users, which allows for an efficient scanning process and facilitates real-time detection. Finally, we conduct a data augmentation scheme to enlarge the training data and apply a lightweight deep learning framework to classify different gestures. Extensive experiments confirm that our system enables multi-user gesture detection and can recognize nine gestures at a distance up to 7 meters.

In a fire emergency, timely and precise firefighting and emergency response significantly rely on rapid fire source location and fire severity assessment. Yet existing fire detection methods have limitations such as environmental interference, inaccurate fire source location, and inability to assess fire severity. We propose UltraFlame, an innovative acoustic fire sensing system that combines the functionality of fire detection, source localization, and fire severity estimation. Our approach utilizes high-frequency ultrasound waves (40kHz) and involves a Two-Stage Sector Beamforming (TSSB) method for real-time fire localization. Additionally, we develop a mathematical model linking fire source distance and severity, enabling real-time fire severity estimation with limited computational complexity. The experimental results suggest that UltraFlame will provide accurate fire source localization and fire severity assessment.

UHF RFID technology becomes increasingly popular in stores, since it can quickly read a large number of RFID tags from afar. The deployed RFID infrastructure, however, does not directly benefit smartphone users in stores, mainly because smartphones cannot read UHF RFID tags or fetch relevant information. This paper aims to bridge the gap and allow users to 'read' UHF RFID tags using their smartphones, without any hardware modification to either deployed RFID systems or smartphone hardware. To ‘read’ an interested tag, a user makes a pre-defined smartphone gesture in front of an interested tag. The smartphone gesture causes changes in 1) RFID measurement data captured by RFID infrastructure, and 2) motion sensor data captured by the user's smartphone. By matching the two data, our system (named ShakeReader) can pair the interested tag with the corresponding smartphone, thereby enabling the smartphone to indirectly 'read' the interested tag. We build a novel reflector polarization model to analyze the impact of smartphone gesture to RFID backscattered signals. We enhance the basic version of ShakeReader [6] by improving its performance in densely deployed scenarios. Experimental results show that ShakeReader can accurately pair interested tags with their corresponding smartphones with an accuracy of >96.3%.

Respiration monitoring (RM) is crucial for tracking various health problems. Recently, RFID has been widely employed for lightweight and low-cost RM. However, existing RFID-based RM systems are designed for static environments where no people move around the monitored person. While, in practice, most environments are dynamic with people moving nearby, which introduces dynamic multipath signals and significantly distorts respiration signal, leading to inaccurate RM. In this paper, we aim to realize accurate RFID-based RM in dynamic environments. Our observations show that multipath signals can result in a similar pattern to respiration, leading to apnea mis-detection and inaccurate respiration rate estimation. To address this issue, we first measure respiration anomaly in the signal spectrogram to detect apnea. Second, we successfully remove the multipath effect for respiration rate estimation inspired by intrinsic features of human respiration. Specifically, compared with peoples moving pattern, respiration pattern is regular and periodic. By transforming a normal respiration cycle into a matched filter, real respiration cycles can be extracted from the noisy RFID signal. Respiration rate is then estimated via peak detection. The experiments show that our system achieves the average error of 4.2% and 0.51bpm for apnea detection and respiration rate estimation in dynamic environments, respectively.

Liquid fraud has plagued people with huge health risks. Liquid fraud detection can help to reduce the risk of liquid hazards. However, existing systems that use biochemical tools or radio frequency signals for liquid sensing are either expensive, intrusive, or inconvenient for public use. In this article, we propose HearLiquid, a low-cost and nonintrusive liquid fraud detection system using commodity acoustic devices. Our insight comes from the fact that acoustic impedance of different liquids results in distinct absorption of the acoustic signal across different frequencies when it travels through the liquid. In specific, we extract the liquid’s acoustic absorption and transmission curve (AATC) over multiple frequencies of the acoustic signal for liquid fraud detection. However, accurately measuring the AATC faces multiple challenges. First, due to the hardware diversity and imperfection, different acoustic devices introduce diverse frequency responses, which brings significant deviations to AATCs of the same liquid. Second, different relative positions between acoustic devices and the liquid container result in variations in the AATC, making the detection result inaccurate. To overcome these challenges, we first calibrate the AATC using a dedicated reference AATC to remove the effect of hardware diversity. To bear the variations in AATCs measured from different relative positions, we apply a well-orchestrated data augmentation technique to automatically generate sufficient AATCs for different positions using a small number of collected data. Finally, AATCs are used to train the liquid detection model. We conduct extensive experiments on many important liquid fraud cases and achieve liquid detection accuracy of 92%–97%.

With the flourish of the smart devices and their applications, controlling devices using gestures has attracted increasing attention for ubiquitous sensing and interaction. Recent works use acoustic signals to track hand movement and recognize gestures. However, they suffer from low robustness due to frequency selective fading, interference and insufficient training data. In this work, we propose RobuCIR, a robust contact-free gesture recognition system that can work under different practical impact factors with high accuracy and robustness. RobuCIR adopts frequency-hopping mechanism to mitigate frequency selective fading and avoid signal interference. To further increase system robustness, we investigate a series of data augmentation techniques based on a small volume of collected data to emulate different practical impact factors. The augmented data is used to effectively train neural network models and cope with various influential factors (e.g., gesture speed, distance to transceiver,etc.). Our experiment results show that RobuCIR can recognize 15 gestures and outperform state-of-the-art works in terms of accuracy and robustness.

UHF RFID technology becomes increasingly popular in RFID-enabled stores (e.g., UNIQLO), since UHF RFID readers can quickly read a large number of RFID tags from afar. The deployed RFID infrastructure, however, does not directly benefit smartphone users in the stores, mainly because smartphones cannot read UHF RFID tags or fetch relevant information (e.g., updated price, real-time promotion). This paper aims to bridge the gap and allow users to `read' UHF RFID tags using their smartphones, without any hardware modification to either deployed RFID systems or smartphone hardware. To `read' an interested tag, a user makes a pre-defined smartphone gesture in front of an interested tag. The smartphone gesture causes changes in 1) RFID measurement data (e.g., phase) captured by RFID infrastructure, and 2) motion sensor data (e.g., accelerometer) captured by the user's smartphone. By matching the two data, our system (named ShakeReader) can pair the interested tag with the corresponding smartphone, thereby enabling the smartphone to indirectly `read' the interested UHF tag. We build a novel reflector polarization model to analyze the impact of smartphone gesture to RFID backscattered signals. Experimental results show that ShakeReader can accurately pair interested tags with their corresponding smartphones with an accuracy of >94.6%.

This article presents the design and implementation of a low-cost software-defined radio-frequency identification (RFID) system for distributed parallel sensing. We aim to implement essential sensing functionalities with low-cost commodity radio components and provide full access to physical layer raw data (e.g., PHY samples of backscatter signals) to enable various RFID sensing applications at low implementation cost. The proposed solution is built in a distributed way where the functionalities of interrogating RFID tags and receiving their backscattered signals are separated into two modules, which naturally supports distributed parallel sensing. A set of innovative techniques is developed, e.g., packet-in-packet communication, carrier frequency offset (CFO) cancellation, self-interference cancellation, etc., to address a range of practical challenges, including RFID command generation with cross technology communication, real-time correction of CFO, etc. We present three case studies enabled by the proposed solution, which demonstrates its applicability and potential of boosting RFID sensing research by substantially cutting the implementation cost of software-defined RFID sensing system.

With the flourish of the smart devices and their applications, controlling devices using gestures has attracted increasing attention for ubiquitous sensing and interaction. Recent works use acoustic signals to track hand movement and recognize gestures. However, they suffer from low robustness due to frequency selective fading, interference and insufficient training data. In this work, we propose RobuCIR, a robust contact-free gesture recognition system that can work under different usage scenarios with high accuracy and robustness. RobuCIR adopts frequency-hopping mechanism to mitigate frequency selective fading and avoid signal interference. To further increase system robustness, we investigate a series of data augmentation techniques based on a small volume of collected data to emulate different usage scenarios. The augmented data is used to effectively train neural network models and cope with various influential factors (e.g., gesture speed, distance to transceiver, etc.). Our experiment results show that RobuCIR can recognize 15 gestures and outperform state-of-the-art works in terms of accuracy and robustness.

Breath monitoring helps assess the general personal health and gives clues to chronic diseases. Yet, current breath monitoring technologies are inconvenient and intrusive. For instance, typical breath monitoring devices need to attach nasal probes or chest bands to users. Wireless sensing technologies have been applied to monitor breathing using radio waves without physical contact. Those wireless sensing technologies however require customized radios which are not readily available. More importantly, due to interference, such technologies do not work well with multiple users. When multiple users are present, the detection accuracy of existing systems decreases dramatically. In this paper, we propose to monitor users' breathing using commercial-off-the-shelf (COTS) RFID systems. In our system, passive lightweight RFID tags are attached to users' clothes and backscatter radio waves, and commodity RFID readers report low level data (e.g., phase values). We reliably detect the effective human respiration corresponded signal and track periodic body movement due to inhaling and exhaling by analyzing the low level data reported by commodity readers. To enhance the measurement robustness, we synthesize data streams from an array of multiple tags to improve the monitoring accuracy. Our design follows the standard EPC protocol which arbitrates collisions in the presence of multiple tags. We implement a prototype for the breath monitoring system with commodity RFID systems. The experiment results show that the prototype system can simultaneously monitor breathing with high accuracy even with the presence of multiple users.

Breath monitoring helps assess the general personal health and gives clues to chronic diseases. Yet current breath monitoring technologies are inconvenient and intrusive. For instance, typical breath monitoring devices need to attach nasal probes or chest bands to users. Wireless sensing technologies have been applied to monitor breathing using radio waves without physical contact. Those wireless sensing technologies however require customized radios which are not readily available. More importantly, due to interference, such technologies do not work well with multiple users. With multiple users in presence, the detection accuracy of existing systems decreases dramatically. In this paper, we propose to monitor users' breathing using commercial-off-the-shelf (COTS) RFID systems. In our system, passive lightweight RFID tags are attached to users' clothes and backscatter radio waves, and commodity RFID readers report low level data (e.g., phase values). We track periodic body movement due to inhaling and exhaling by analyzing the low level data reported by commodity readers. To enhance the measurement robustness, we synthesize data streams from an array of multiple tags to improve the monitoring accuracy. Our design follows the standard EPC protocol which arbitrates collisions in the presence of multiple tags. We implement a prototype the breath monitoring system with commodity RFID systems. The experiment results show that the prototype system can simultaneously monitor breathing with high accuracy even with the presence of multiple users.

Abstract Security issue in Internet of Things (IoTs) has long been the topic of extensive research in the last decade. Data encryption and authentication are the most common two methods to address the security issues in IoTs. However, these efforts are ineffective in detecting the diverse malicious attacks, especially in intrusion detection. Comparatively, very few attentions have been paid for detecting intrusive nodes in IoTs research. Therefore, in this paper, we derive an innovative method called granulometric size distribution (GSD) method based on mathematical morphology for detecting malicious attack in IoTs, such as intrusion detection. We successfully generate GSD clusters to directly monitor the number of active nodes in a wireless sensor network because the GSD curves are similar when the number of active nodes in a wireless sensor network is fixed. Link Quality Indicator data of each node are utilized as the network parameters in this method. The results show the effectiveness in intrusion detection. Copyright © 2015 John Wiley & Sons, Ltd.

We propose a SDN-like architecture based WSN and improve the existing EC-CKN Sleep Scheduling mechanism to implement more efficient energy management. A SDN-like architecture is adopted instead of traditional WSN architecture and EC-CKN algorithm is applied as the fundamental algorithm. This paper presents the design, implementation and evaluation of the proposed SDN-ECCKN on the WSN with SDN-like architecture.

Software Defined Network (SDN) has long been a research focus since born from the lab of Stanford University. Researches on traditional home networks are faced with a series of challenges due to the ever more complicated user demands. The application of SDN to the home network is an effective approach in coping with it. Now the research on the SDN based home network is in its preliminary stage. Therefore, for better user experience, it is essential to effectively manage and utilize the resources of the home network. The general slicing strategies don't show much advantage in performance within the home networks due to the increased user demands and applications. In this paper, we introduce an advanced SDN based home network prototype and analyze its compositions and application requirements. By implementing and comparing several slicing strategies in properties, we achieve an optimized slicing strategy according to the specified home network circumstance and our preference.